TeeZee
/

DarkForest-20B-v1.1

Text Generation

Not-For-All-Audiences

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

TeeZee commited on Feb 12

Commit

eef199a

•

1 Parent(s): ca708f8

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ tags:
 - To create this model two step procedure was used. First a new 20B model was created using [microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b)
   and [KoboldAI/LLaMA2-13B-Erebus-v3](https://huggingface.co/KoboldAI/LLaMA2-13B-Erebus-v3) , deatils of the merge in [mergekit-config_step1.yml](https://huggingface.co/TeeZee/DarkForest-20B-v1.0/resolve/main/mergekit-config_step1.yml)
-- then [jebcarter/psyonic-cetacean-20B](https://huggingface.co/jebcarter/psyonic-cetacean-20B) was used to produce the final model, merge config in [mergekit-config_step2.yml](https://huggingface.co/TeeZee/DarkForest-20B-v1.1/resolve/main/mergekit-config_step2.yml)
 - instead of linear merge method used in v1.0, this time DARE TIES method was used for step2
 - The resulting model has approximately 20 billion parameters.

 - To create this model two step procedure was used. First a new 20B model was created using [microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b)
   and [KoboldAI/LLaMA2-13B-Erebus-v3](https://huggingface.co/KoboldAI/LLaMA2-13B-Erebus-v3) , deatils of the merge in [mergekit-config_step1.yml](https://huggingface.co/TeeZee/DarkForest-20B-v1.0/resolve/main/mergekit-config_step1.yml)
+- then [jebcarter/psyonic-cetacean-20B](https://huggingface.co/jebcarter/psyonic-cetacean-20B) was used to produce the final model, merge config in [mergekit-config-step2.yml](https://huggingface.co/TeeZee/DarkForest-20B-v1.1/resolve/main/mergekit-config-step2.yml)
 - instead of linear merge method used in v1.0, this time DARE TIES method was used for step2
 - The resulting model has approximately 20 billion parameters.